Super-squash branch 'main' using huggingface_hub

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,116 @@
+---
+base_model:
+- Qwen/Qwen3.8-27B
+license: apache-2.0
+tags:
+- unsloth
+---
+
+# Read our How to [Run Qwen3.8-27B Guide!](https://unsloth.ai/docs/models/qwen3.8)
+<div>
+  <p style="margin: 0 0 0px 0; margin-top: 0px;">
+    <em>This NVFP4 quant uses Unsloth Dynamic V3.0 (preview) for SOTA quantization performance.</em>
+  </p>
+  <div style="display: flex; gap: 5px; align-items: center; margin-bottom: 0px;">
+    <a href="https://github.com/unslothai/unsloth/">
+      <img src="https://github.com/unslothai/unsloth/raw/main/images/unsloth%20new%20logo.png" width="133">
+    </a>
+    <a href="https://discord.gg/unsloth">
+      <img src="https://github.com/unslothai/unsloth/raw/main/images/Discord%20button.png" width="173">
+    </a>
+    <a href="https://unsloth.ai/docs/models/qwen3.8">
+      <img src="https://raw.githubusercontent.com/unslothai/unsloth/refs/heads/main/images/documentation%20green%20button.png" width="143">
+    </a>
+  </div>
+    <ul style="margin: 0;">
+    <li>Developer Role Support so Qwen3.8 can work in agentic tools like Codex and more!</li>
+    <li>MTP for fast inference is available.</li>
+    <li>Qwen3.8 can now be run and fine-tuned in <a href="https://unsloth.ai/docs/new/desktop">Unsloth Desktop</a>. <a href="https://unsloth.ai/docs/models/qwen3.8">Read our guide</a>.</li>
+    <li>Tool calling improvements: Makes parsing nested objects to make tool calling succeed more.</li>
+   <li>See below for 4-bit Qwen3.8-27B run inside of Unsloth Desktop:</li>
+</div>
+
+<img width="600" alt="qwen3.8 unsloth desktop" src="https://3215535692-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FxhOjnexMCB3dmuQFQ2Zq%2Fuploads%2FSqxs6NjShWrLfRKhDy1m%2Fvolcano%202.gif?alt=media&token=395274a0-b437-403a-8a01-8e8502f9d225" />
+
+
+
+---
+
+# Qwen3.8-27B
+
+Following the widespread community adoption of the Qwen3.5 and Qwen3.6 series, we are pleased to introduce Qwen3.8, the most capable generation in the Qwen open-model family to date.
+
+Built on the architectural foundation of Qwen3.5, Qwen3.8 delivers substantial gains across coding, professional work, research, and long-horizon agentic tasks. Qwen3.8-27B brings these advances to a compact, deployment-friendly dense model: a native vision-language model that understands images and videos, with flexible thinking control, designed to carry complex, multi-step tasks through to completion with greater reliability.
+
+## Qwen3.8 Highlights
+
+Qwen3.8-27B features the following enhancements:
+- **Core Capabilities**: Comprehensive improvements across coding, professional work, research, and long-horizon agentic tasks.
+- **Agent Execution**: Stronger autonomous planning and better handling of environment feedback, leading to more reliable end-to-end task completion.
+- **Downstream Compatibility**: Broader support for popular harnesses and development tools, making it easier to integrate into your existing stack.
+- **Flexible Thinking Control**: Thinking mode is on by default and can be disabled per request; reasoning depth can be tuned with `reasoning_effort`, and reasoning context from historical messages is retained via `preserve_thinking`.
+- **Vision-Language Understanding**: Native support for image and video understanding, from STEM diagrams and documents to hour-scale videos.
+
+
+## Model Overview
+
+- Type: Causal Language Model with Vision Encoder
+- Training Stage: Pre-training & Post-training
+- Language Model
+    - Number of Parameters: 27B
+    - Hidden Dimension: 5120
+    - Token Embedding: 248,320 (Padded)
+    - Number of Layers: 64
+    - Hidden Layout: 16 × (3 × (Gated DeltaNet → FFN) → 1 × (Gated Attention → FFN))
+    - Gated DeltaNet:
+        - Number of Linear Attention Heads: 48 for V and 16 for QK
+        - Head Dimension: 128
+    - Gated Attention:
+        - Number of Attention Heads: 24 for Q and 4 for KV
+        - Head Dimension: 256
+        - Rotary Position Embedding Dimension: 64
+    - Feed Forward Network:
+        - Intermediate Dimension: 17,408
+    - LM Output: 248,320 (Padded)
+    - MTP (Multi-Token Prediction): trained with multiple steps
+- Context Length: 262,144 natively and extensible up to 1,000,000 tokens.
+
+## Best Practices
+
+To achieve optimal performance, we recommend the following settings:
+
+1. **Sampling Parameters**: We suggest using the following sets of sampling parameters:  
+    
+    - Thinking Mode: `temperature=1.0`, `top_p=0.95`, `top_k=20`, `min_p=0.0`, `presence_penalty=0.0`, `repetition_penalty=1.0`
+    - Instruct (or non-thinking) mode: `temperature=0.7`, `top_p=0.80`, `top_k=20`, `min_p=0.0`, `presence_penalty=1.5`, `repetition_penalty=1.0`
+    
+    For supported frameworks, you can adjust the `presence_penalty` parameter between 0 and 2 to reduce endless repetition. However, using a higher value may occasionally result in language mixing and a slight decrease in model performance.
+
+2. **Adequate Output Length**: To optimize performance on agentic tasks, we recommend allocating sufficient output length to allow the model to generate detailed and comprehensive responses. For frameworks that support separate token limits for internal reasoning and final outputs, we suggest the following configuration within the 1M context length:
+    
+    - Reasoning Content: Set the maximum output length to 262,144 tokens.
+    - Final Response: Set the maximum output length to 131,072 tokens.
+
+    These settings provide the necessary capacity for complex reasoning while ensuring ample space for high-quality final deliverables.
+
+3. **Processing Ultra-Long Texts**: Qwen3.8-27B natively supports context lengths of up to 262,144 tokens. For long-horizon tasks where the total length (including both input and output) exceeds this limit, we recommend using RoPE scaling techniques to handle long texts effectively, e.g., YaRN.
+
+4. **Long Video Understanding**: To optimize inference efficiency for plain text and images, the `size` parameter in the released `video_preprocessor_config.json` is conservatively configured. It is recommended to set the `longest_edge` parameter in the video_preprocessor_config file to 469,762,048 (corresponding to 224k video tokens) to enable higher frame-rate sampling for hour-scale videos and thereby achieve superior performance. For example,
+    ```json
+    {"longest_edge": 469762048, "shortest_edge": 4096}
+    ```
+
+## Citation
+
+If you find our work helpful, feel free to give us a cite.
+
+
+```bibtex
+@misc{qwen38,
+    title = {{Qwen3.8-Max}: A New Bar for Coding and Cowork},
+    url = {https://qwen.ai/blog?id=qwen3.8},
+    author = {{Qwen Team}},
+    month = {August},
+    year = {2026}
+}
+```

chat_template.jinja

@@ -0,0 +1,184 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- set sysns = namespace(count=0, text='') %}
+{%- for message in messages %}
+    {%- if sysns.count == loop.index0 and (message.role == 'system' or message.role == 'developer') %}
+        {%- set sys_content = render_content(message.content, false, true)|trim %}
+        {%- if sys_content %}
+            {%- set sysns.text = sysns.text + ('\n' if sysns.text else '') + sys_content %}
+        {%- endif %}
+        {%- set sysns.count = sysns.count + 1 %}
+    {%- endif %}
+{%- endfor %}
+{%- set num_sys = sysns.count %}
+{%- set merged_system = sysns.text %}
+{%- set reasoning_instructions = '' %}
+{%- if enable_thinking is undefined or enable_thinking is true %}
+    {%- set resolved_reasoning_effort = reasoning_effort|default('xhigh') %}
+    {%- if resolved_reasoning_effort == 'high' %}
+        {%- set resolved_reasoning_effort = 'xhigh' %}
+    {%- endif %}
+    {%- if resolved_reasoning_effort not in ('xhigh', 'medium', 'low') %}
+        {{- raise_exception('Unexpected reasoning effort ' ~ reasoning_effort ~ '. Supported types are xhigh (default), medium, and low.') }}
+    {%- endif %}
+    {%- if resolved_reasoning_effort == 'xhigh' %}
+        {%- set reasoning_instructions = 'Reasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.' %}
+    {%- elif resolved_reasoning_effort == 'low' %}
+        {%- set reasoning_instructions = 'Reasoning effort is set to low. Keep your thinking brief and focused, moving directly to the conclusion without unnecessary elaboration.' %}
+    {%- endif %}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {%- if reasoning_instructions %}
+        {{- reasoning_instructions + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if merged_system %}
+        {{- '\n\n' + merged_system }}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if merged_system %}
+        {{- '<|im_start|>system\n' + (reasoning_instructions + '\n\n' if reasoning_instructions else '')  + merged_system + '<|im_end|>\n' }}
+    {%- elif reasoning_instructions %}
+        {{- '<|im_start|>system\n' + reasoning_instructions + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if loop.index0 >= num_sys %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" or message.role == "developer" %}
+        {{- raise_exception('System message must be at the beginning.') }}
+    {%- elif message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if preserve_thinking is undefined or preserve_thinking is true or loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if tool_call.name is not defined or tool_call.name is none %}
+                    {{- raise_exception('Tool call is missing a function name.') }}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is mapping %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- elif tool_call.arguments is string %}
+                    {%- if tool_call.arguments|trim %}
+                        {{- raise_exception('Tool call arguments for function "' + (tool_call.name | string) + '" were passed as a JSON string. Parse them into an object before calling apply_chat_template.') }}
+                    {%- endif %}
+                {%- elif tool_call.arguments is defined and tool_call.arguments is not none %}
+                    {{- raise_exception('Tool call arguments for function "' + (tool_call.name | string) + '" must be an object/mapping or a JSON string.') }}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}
+{#- Unsloth fixes - developer role, merged system messages, tool calling #}

config.json

@@ -0,0 +1,547 @@
+{
+  "architectures": [
+    "Qwen3_5ForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "head_dim": 256,
+  "image_token_id": 248056,
+  "language_model_only": false,
+  "model_type": "qwen3_5",
+  "num_attention_heads": 24,
+  "num_key_value_heads": 4,
+  "quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "format": "float-quantized",
+        "input_activations": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": true,
+          "group_size": null,
+          "num_bits": 8,
+          "observer": null,
+          "observer_kwargs": {},
+          "scale_dtype": null,
+          "strategy": "token",
+          "symmetric": true,
+          "type": "float",
+          "zp_dtype": null
+        },
+        "output_activations": null,
+        "targets": [
+          "re:.*self_attn\\.(q|k|v|o)_proj$",
+          "re:.*linear_attn\\.(in_proj_qkv|in_proj_z|out_proj)$",
+          "re:.*lm_head",
+          "re:.*layers\\.(56|57|58|59|60|61|62|63)\\.mlp\\.(gate|up|down)_proj$"
+        ],
+        "weights": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": false,
+          "group_size": null,
+          "num_bits": 8,
+          "observer": "memoryless_minmax",
+          "observer_kwargs": {},
+          "scale_dtype": null,
+          "strategy": "channel",
+          "symmetric": true,
+          "type": "float",
+          "zp_dtype": null
+        }
+      },
+      "group_1": {
+        "format": "nvfp4-pack-quantized",
+        "input_activations": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": "local",
+          "group_size": 16,
+          "num_bits": 4,
+          "observer": "static_minmax",
+          "observer_kwargs": {},
+          "scale_dtype": "torch.float8_e4m3fn",
+          "strategy": "tensor_group",
+          "symmetric": true,
+          "type": "float",
+          "zp_dtype": null
+        },
+        "output_activations": null,
+        "targets": [
+          "re:.*mlp\\.(gate|up|down)_proj$"
+        ],
+        "weights": {
+          "actorder": "static",
+          "block_structure": null,
+          "dynamic": false,
+          "group_size": 16,
+          "num_bits": 4,
+          "observer_kwargs": {},
+          "scale_dtype": "torch.float8_e4m3fn",
+          "strategy": "tensor_group",
+          "symmetric": true,
+          "type": "float",
+          "zp_dtype": null
+        }
+      }
+    },
+    "format": "mixed-precision",
+    "global_compression_ratio": null,
+    "ignore": [
+      "model.visual.blocks.0.attn.qkv",
+      "model.visual.blocks.0.attn.proj",
+      "model.visual.blocks.0.mlp.linear_fc1",
+      "model.visual.blocks.0.mlp.linear_fc2",
+      "model.visual.blocks.1.attn.qkv",
+      "model.visual.blocks.1.attn.proj",
+      "model.visual.blocks.1.mlp.linear_fc1",
+      "model.visual.blocks.1.mlp.linear_fc2",
+      "model.visual.blocks.2.attn.qkv",
+      "model.visual.blocks.2.attn.proj",
+      "model.visual.blocks.2.mlp.linear_fc1",
+      "model.visual.blocks.2.mlp.linear_fc2",
+      "model.visual.blocks.3.attn.qkv",
+      "model.visual.blocks.3.attn.proj",
+      "model.visual.blocks.3.mlp.linear_fc1",
+      "model.visual.blocks.3.mlp.linear_fc2",
+      "model.visual.blocks.4.attn.qkv",
+      "model.visual.blocks.4.attn.proj",
+      "model.visual.blocks.4.mlp.linear_fc1",
+      "model.visual.blocks.4.mlp.linear_fc2",
+      "model.visual.blocks.5.attn.qkv",
+      "model.visual.blocks.5.attn.proj",
+      "model.visual.blocks.5.mlp.linear_fc1",
+      "model.visual.blocks.5.mlp.linear_fc2",
+      "model.visual.blocks.6.attn.qkv",
+      "model.visual.blocks.6.attn.proj",
+      "model.visual.blocks.6.mlp.linear_fc1",
+      "model.visual.blocks.6.mlp.linear_fc2",
+      "model.visual.blocks.7.attn.qkv",
+      "model.visual.blocks.7.attn.proj",
+      "model.visual.blocks.7.mlp.linear_fc1",
+      "model.visual.blocks.7.mlp.linear_fc2",
+      "model.visual.blocks.8.attn.qkv",
+      "model.visual.blocks.8.attn.proj",
+      "model.visual.blocks.8.mlp.linear_fc1",
+      "model.visual.blocks.8.mlp.linear_fc2",
+      "model.visual.blocks.9.attn.qkv",
+      "model.visual.blocks.9.attn.proj",
+      "model.visual.blocks.9.mlp.linear_fc1",
+      "model.visual.blocks.9.mlp.linear_fc2",
+      "model.visual.blocks.10.attn.qkv",
+      "model.visual.blocks.10.attn.proj",
+      "model.visual.blocks.10.mlp.linear_fc1",
+      "model.visual.blocks.10.mlp.linear_fc2",
+      "model.visual.blocks.11.attn.qkv",
+      "model.visual.blocks.11.attn.proj",
+      "model.visual.blocks.11.mlp.linear_fc1",
+      "model.visual.blocks.11.mlp.linear_fc2",
+      "model.visual.blocks.12.attn.qkv",
+      "model.visual.blocks.12.attn.proj",
+      "model.visual.blocks.12.mlp.linear_fc1",
+      "model.visual.blocks.12.mlp.linear_fc2",
+      "model.visual.blocks.13.attn.qkv",
+      "model.visual.blocks.13.attn.proj",
+      "model.visual.blocks.13.mlp.linear_fc1",
+      "model.visual.blocks.13.mlp.linear_fc2",
+      "model.visual.blocks.14.attn.qkv",
+      "model.visual.blocks.14.attn.proj",
+      "model.visual.blocks.14.mlp.linear_fc1",
+      "model.visual.blocks.14.mlp.linear_fc2",
+      "model.visual.blocks.15.attn.qkv",
+      "model.visual.blocks.15.attn.proj",
+      "model.visual.blocks.15.mlp.linear_fc1",
+      "model.visual.blocks.15.mlp.linear_fc2",
+      "model.visual.blocks.16.attn.qkv",
+      "model.visual.blocks.16.attn.proj",
+      "model.visual.blocks.16.mlp.linear_fc1",
+      "model.visual.blocks.16.mlp.linear_fc2",
+      "model.visual.blocks.17.attn.qkv",
+      "model.visual.blocks.17.attn.proj",
+      "model.visual.blocks.17.mlp.linear_fc1",
+      "model.visual.blocks.17.mlp.linear_fc2",
+      "model.visual.blocks.18.attn.qkv",
+      "model.visual.blocks.18.attn.proj",
+      "model.visual.blocks.18.mlp.linear_fc1",
+      "model.visual.blocks.18.mlp.linear_fc2",
+      "model.visual.blocks.19.attn.qkv",
+      "model.visual.blocks.19.attn.proj",
+      "model.visual.blocks.19.mlp.linear_fc1",
+      "model.visual.blocks.19.mlp.linear_fc2",
+      "model.visual.blocks.20.attn.qkv",
+      "model.visual.blocks.20.attn.proj",
+      "model.visual.blocks.20.mlp.linear_fc1",
+      "model.visual.blocks.20.mlp.linear_fc2",
+      "model.visual.blocks.21.attn.qkv",
+      "model.visual.blocks.21.attn.proj",
+      "model.visual.blocks.21.mlp.linear_fc1",
+      "model.visual.blocks.21.mlp.linear_fc2",
+      "model.visual.blocks.22.attn.qkv",
+      "model.visual.blocks.22.attn.proj",
+      "model.visual.blocks.22.mlp.linear_fc1",
+      "model.visual.blocks.22.mlp.linear_fc2",
+      "model.visual.blocks.23.attn.qkv",
+      "model.visual.blocks.23.attn.proj",
+      "model.visual.blocks.23.mlp.linear_fc1",
+      "model.visual.blocks.23.mlp.linear_fc2",
+      "model.visual.blocks.24.attn.qkv",
+      "model.visual.blocks.24.attn.proj",
+      "model.visual.blocks.24.mlp.linear_fc1",
+      "model.visual.blocks.24.mlp.linear_fc2",
+      "model.visual.blocks.25.attn.qkv",
+      "model.visual.blocks.25.attn.proj",
+      "model.visual.blocks.25.mlp.linear_fc1",
+      "model.visual.blocks.25.mlp.linear_fc2",
+      "model.visual.blocks.26.attn.qkv",
+      "model.visual.blocks.26.attn.proj",
+      "model.visual.blocks.26.mlp.linear_fc1",
+      "model.visual.blocks.26.mlp.linear_fc2",
+      "model.visual.merger.linear_fc1",
+      "model.visual.merger.linear_fc2",
+      "model.language_model.layers.0.linear_attn",
+      "model.language_model.layers.0.linear_attn.norm",
+      "model.language_model.layers.0.linear_attn.in_proj_b",
+      "model.language_model.layers.0.linear_attn.in_proj_a",
+      "model.language_model.layers.1.linear_attn",
+      "model.language_model.layers.1.linear_attn.norm",
+      "model.language_model.layers.1.linear_attn.in_proj_b",
+      "model.language_model.layers.1.linear_attn.in_proj_a",
+      "model.language_model.layers.2.linear_attn",
+      "model.language_model.layers.2.linear_attn.norm",
+      "model.language_model.layers.2.linear_attn.in_proj_b",
+      "model.language_model.layers.2.linear_attn.in_proj_a",
+      "model.language_model.layers.4.linear_attn",
+      "model.language_model.layers.4.linear_attn.norm",
+      "model.language_model.layers.4.linear_attn.in_proj_b",
+      "model.language_model.layers.4.linear_attn.in_proj_a",
+      "model.language_model.layers.5.linear_attn",
+      "model.language_model.layers.5.linear_attn.norm",
+      "model.language_model.layers.5.linear_attn.in_proj_b",
+      "model.language_model.layers.5.linear_attn.in_proj_a",
+      "model.language_model.layers.6.linear_attn",
+      "model.language_model.layers.6.linear_attn.norm",
+      "model.language_model.layers.6.linear_attn.in_proj_b",
+      "model.language_model.layers.6.linear_attn.in_proj_a",
+      "model.language_model.layers.8.linear_attn",
+      "model.language_model.layers.8.linear_attn.norm",
+      "model.language_model.layers.8.linear_attn.in_proj_b",
+      "model.language_model.layers.8.linear_attn.in_proj_a",
+      "model.language_model.layers.9.linear_attn",
+      "model.language_model.layers.9.linear_attn.norm",
+      "model.language_model.layers.9.linear_attn.in_proj_b",
+      "model.language_model.layers.9.linear_attn.in_proj_a",
+      "model.language_model.layers.10.linear_attn",
+      "model.language_model.layers.10.linear_attn.norm",
+      "model.language_model.layers.10.linear_attn.in_proj_b",
+      "model.language_model.layers.10.linear_attn.in_proj_a",
+      "model.language_model.layers.12.linear_attn",
+      "model.language_model.layers.12.linear_attn.norm",
+      "model.language_model.layers.12.linear_attn.in_proj_b",
+      "model.language_model.layers.12.linear_attn.in_proj_a",
+      "model.language_model.layers.13.linear_attn",
+      "model.language_model.layers.13.linear_attn.norm",
+      "model.language_model.layers.13.linear_attn.in_proj_b",
+      "model.language_model.layers.13.linear_attn.in_proj_a",
+      "model.language_model.layers.14.linear_attn",
+      "model.language_model.layers.14.linear_attn.norm",
+      "model.language_model.layers.14.linear_attn.in_proj_b",
+      "model.language_model.layers.14.linear_attn.in_proj_a",
+      "model.language_model.layers.16.linear_attn",
+      "model.language_model.layers.16.linear_attn.norm",
+      "model.language_model.layers.16.linear_attn.in_proj_b",
+      "model.language_model.layers.16.linear_attn.in_proj_a",
+      "model.language_model.layers.17.linear_attn",
+      "model.language_model.layers.17.linear_attn.norm",
+      "model.language_model.layers.17.linear_attn.in_proj_b",
+      "model.language_model.layers.17.linear_attn.in_proj_a",
+      "model.language_model.layers.18.linear_attn",
+      "model.language_model.layers.18.linear_attn.norm",
+      "model.language_model.layers.18.linear_attn.in_proj_b",
+      "model.language_model.layers.18.linear_attn.in_proj_a",
+      "model.language_model.layers.20.linear_attn",
+      "model.language_model.layers.20.linear_attn.norm",
+      "model.language_model.layers.20.linear_attn.in_proj_b",
+      "model.language_model.layers.20.linear_attn.in_proj_a",
+      "model.language_model.layers.21.linear_attn",
+      "model.language_model.layers.21.linear_attn.norm",
+      "model.language_model.layers.21.linear_attn.in_proj_b",
+      "model.language_model.layers.21.linear_attn.in_proj_a",
+      "model.language_model.layers.22.linear_attn",
+      "model.language_model.layers.22.linear_attn.norm",
+      "model.language_model.layers.22.linear_attn.in_proj_b",
+      "model.language_model.layers.22.linear_attn.in_proj_a",
+      "model.language_model.layers.24.linear_attn",
+      "model.language_model.layers.24.linear_attn.norm",
+      "model.language_model.layers.24.linear_attn.in_proj_b",
+      "model.language_model.layers.24.linear_attn.in_proj_a",
+      "model.language_model.layers.25.linear_attn",
+      "model.language_model.layers.25.linear_attn.norm",
+      "model.language_model.layers.25.linear_attn.in_proj_b",
+      "model.language_model.layers.25.linear_attn.in_proj_a",
+      "model.language_model.layers.26.linear_attn",
+      "model.language_model.layers.26.linear_attn.norm",
+      "model.language_model.layers.26.linear_attn.in_proj_b",
+      "model.language_model.layers.26.linear_attn.in_proj_a",
+      "model.language_model.layers.28.linear_attn",
+      "model.language_model.layers.28.linear_attn.norm",
+      "model.language_model.layers.28.linear_attn.in_proj_b",
+      "model.language_model.layers.28.linear_attn.in_proj_a",
+      "model.language_model.layers.29.linear_attn",
+      "model.language_model.layers.29.linear_attn.norm",
+      "model.language_model.layers.29.linear_attn.in_proj_b",
+      "model.language_model.layers.29.linear_attn.in_proj_a",
+      "model.language_model.layers.30.linear_attn",
+      "model.language_model.layers.30.linear_attn.norm",
+      "model.language_model.layers.30.linear_attn.in_proj_b",
+      "model.language_model.layers.30.linear_attn.in_proj_a",
+      "model.language_model.layers.32.linear_attn",
+      "model.language_model.layers.32.linear_attn.norm",
+      "model.language_model.layers.32.linear_attn.in_proj_b",
+      "model.language_model.layers.32.linear_attn.in_proj_a",
+      "model.language_model.layers.33.linear_attn",
+      "model.language_model.layers.33.linear_attn.norm",
+      "model.language_model.layers.33.linear_attn.in_proj_b",
+      "model.language_model.layers.33.linear_attn.in_proj_a",
+      "model.language_model.layers.34.linear_attn",
+      "model.language_model.layers.34.linear_attn.norm",
+      "model.language_model.layers.34.linear_attn.in_proj_b",
+      "model.language_model.layers.34.linear_attn.in_proj_a",
+      "model.language_model.layers.36.linear_attn",
+      "model.language_model.layers.36.linear_attn.norm",
+      "model.language_model.layers.36.linear_attn.in_proj_b",
+      "model.language_model.layers.36.linear_attn.in_proj_a",
+      "model.language_model.layers.37.linear_attn",
+      "model.language_model.layers.37.linear_attn.norm",
+      "model.language_model.layers.37.linear_attn.in_proj_b",
+      "model.language_model.layers.37.linear_attn.in_proj_a",
+      "model.language_model.layers.38.linear_attn",
+      "model.language_model.layers.38.linear_attn.norm",
+      "model.language_model.layers.38.linear_attn.in_proj_b",
+      "model.language_model.layers.38.linear_attn.in_proj_a",
+      "model.language_model.layers.40.linear_attn",
+      "model.language_model.layers.40.linear_attn.norm",
+      "model.language_model.layers.40.linear_attn.in_proj_b",
+      "model.language_model.layers.40.linear_attn.in_proj_a",
+      "model.language_model.layers.41.linear_attn",
+      "model.language_model.layers.41.linear_attn.norm",
+      "model.language_model.layers.41.linear_attn.in_proj_b",
+      "model.language_model.layers.41.linear_attn.in_proj_a",
+      "model.language_model.layers.42.linear_attn",
+      "model.language_model.layers.42.linear_attn.norm",
+      "model.language_model.layers.42.linear_attn.in_proj_b",
+      "model.language_model.layers.42.linear_attn.in_proj_a",
+      "model.language_model.layers.44.linear_attn",
+      "model.language_model.layers.44.linear_attn.norm",
+      "model.language_model.layers.44.linear_attn.in_proj_b",
+      "model.language_model.layers.44.linear_attn.in_proj_a",
+      "model.language_model.layers.45.linear_attn",
+      "model.language_model.layers.45.linear_attn.norm",
+      "model.language_model.layers.45.linear_attn.in_proj_b",
+      "model.language_model.layers.45.linear_attn.in_proj_a",
+      "model.language_model.layers.46.linear_attn",
+      "model.language_model.layers.46.linear_attn.norm",
+      "model.language_model.layers.46.linear_attn.in_proj_b",
+      "model.language_model.layers.46.linear_attn.in_proj_a",
+      "model.language_model.layers.48.linear_attn",
+      "model.language_model.layers.48.linear_attn.norm",
+      "model.language_model.layers.48.linear_attn.in_proj_b",
+      "model.language_model.layers.48.linear_attn.in_proj_a",
+      "model.language_model.layers.49.linear_attn",
+      "model.language_model.layers.49.linear_attn.norm",
+      "model.language_model.layers.49.linear_attn.in_proj_b",
+      "model.language_model.layers.49.linear_attn.in_proj_a",
+      "model.language_model.layers.50.linear_attn",
+      "model.language_model.layers.50.linear_attn.norm",
+      "model.language_model.layers.50.linear_attn.in_proj_b",
+      "model.language_model.layers.50.linear_attn.in_proj_a",
+      "model.language_model.layers.52.linear_attn",
+      "model.language_model.layers.52.linear_attn.norm",
+      "model.language_model.layers.52.linear_attn.in_proj_b",
+      "model.language_model.layers.52.linear_attn.in_proj_a",
+      "model.language_model.layers.53.linear_attn",
+      "model.language_model.layers.53.linear_attn.norm",
+      "model.language_model.layers.53.linear_attn.in_proj_b",
+      "model.language_model.layers.53.linear_attn.in_proj_a",
+      "model.language_model.layers.54.linear_attn",
+      "model.language_model.layers.54.linear_attn.norm",
+      "model.language_model.layers.54.linear_attn.in_proj_b",
+      "model.language_model.layers.54.linear_attn.in_proj_a",
+      "model.language_model.layers.56.linear_attn",
+      "model.language_model.layers.56.linear_attn.norm",
+      "model.language_model.layers.56.linear_attn.in_proj_b",
+      "model.language_model.layers.56.linear_attn.in_proj_a",
+      "model.language_model.layers.57.linear_attn",
+      "model.language_model.layers.57.linear_attn.norm",
+      "model.language_model.layers.57.linear_attn.in_proj_b",
+      "model.language_model.layers.57.linear_attn.in_proj_a",
+      "model.language_model.layers.58.linear_attn",
+      "model.language_model.layers.58.linear_attn.norm",
+      "model.language_model.layers.58.linear_attn.in_proj_b",
+      "model.language_model.layers.58.linear_attn.in_proj_a",
+      "model.language_model.layers.60.linear_attn",
+      "model.language_model.layers.60.linear_attn.norm",
+      "model.language_model.layers.60.linear_attn.in_proj_b",
+      "model.language_model.layers.60.linear_attn.in_proj_a",
+      "model.language_model.layers.61.linear_attn",
+      "model.language_model.layers.61.linear_attn.norm",
+      "model.language_model.layers.61.linear_attn.in_proj_b",
+      "model.language_model.layers.61.linear_attn.in_proj_a",
+      "model.language_model.layers.62.linear_attn",
+      "model.language_model.layers.62.linear_attn.norm",
+      "model.language_model.layers.62.linear_attn.in_proj_b",
+      "model.language_model.layers.62.linear_attn.in_proj_a",
+      "re:^mtp.*"
+    ],
+    "kv_cache_scheme": {
+      "actorder": null,
+      "block_structure": null,
+      "dynamic": false,
+      "group_size": null,
+      "num_bits": 8,
+      "observer": "static_minmax",
+      "observer_kwargs": {},
+      "scale_dtype": null,
+      "strategy": "tensor",
+      "symmetric": true,
+      "type": "float",
+      "zp_dtype": null
+    },
+    "quant_method": "compressed-tensors",
+    "quantization_status": "compressed",
+    "sparsity_config": {},
+    "transform_config": {},
+    "version": "0.17.2.a20260716"
+  },
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_output_gate": true,
+    "bos_token_id": 248044,
+    "dtype": "bfloat16",
+    "eos_token_id": 248044,
+    "full_attention_interval": 4,
+    "head_dim": 256,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 17408,
+    "layer_types": [
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention"
+    ],
+    "linear_conv_kernel_dim": 4,
+    "linear_key_head_dim": 128,
+    "linear_num_key_heads": 16,
+    "linear_num_value_heads": 48,
+    "linear_value_head_dim": 128,
+    "mamba_ssm_dtype": "float32",
+    "max_position_embeddings": 262144,
+    "model_type": "qwen3_5_text",
+    "mtp_num_hidden_layers": 1,
+    "mtp_use_dedicated_embeddings": false,
+    "num_attention_heads": 24,
+    "num_hidden_layers": 64,
+    "num_key_value_heads": 4,
+    "output_gate_type": "swish",
+    "pad_token_id": null,
+    "partial_rotary_factor": 0.25,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        11,
+        11,
+        10
+      ],
+      "partial_rotary_factor": 0.25,
+      "rope_theta": 10000000,
+      "rope_type": "default"
+    },
+    "tie_word_embeddings": false,
+    "use_cache": true,
+    "vocab_size": 248320
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.14.1",
+  "video_token_id": 248057,
+  "vision_config": {
+    "deepstack_visual_indexes": [],
+    "depth": 27,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4304,
+    "model_type": "qwen3_5_vision",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 5120,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 248054,
+  "vision_start_token_id": 248053
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 248044,
+  "do_sample": true,
+  "eos_token_id": [
+    248046,
+    248044
+  ],
+  "pad_token_id": 248044,
+  "temperature": 1.0,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "5.14.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c473512c70eace07e2256fe9fd76596ac03e3295bee7d54cfb72676416afcc05
+size 22568192096

model_mtp.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d8268aa85ace093a561e3e7b63b9d390dac1cd55a90cd55b5ec509c3c9da9fe
+size 849400392

preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+    "size": {
+        "longest_edge": 16777216,
+        "shortest_edge": 65536
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "image_processor_type": "Qwen2VLImageProcessorFast"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
+size 19989325

tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}

video_preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+    "size": {
+        "longest_edge": 25165824,
+        "shortest_edge": 4096
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "video_processor_type": "Qwen3VLVideoProcessor"
+}